PerceptionGPT: Effectively Fusing Visual Perception into LLM von Pi, Renjie, Yao, Lewei, Gao, Jiahui, Zhang, Jipeng, Zhang, Tong

Volltext bestellen

DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detection von Yao, Lewei, Pi, Renjie, Han, Jianhua, Liang, Xiaodan, Xu, Hang, Zhang, Wei, Li, Zhenguo, Xu, Dan

Volltext bestellen

DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation von Mo, Shentong, Xie, Enze, Chu, Ruihang, Yao, Lewei, Hong, Lanqing, Nießner, Matthias, Li, Zhenguo

Volltext bestellen

PixArt-\Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation von Chen, Junsong, Ge, Chongjian, Xie, Enze, Wu, Yue, Yao, Lewei, Ren, Xiaozhe, Wang, Zhongdao, Luo, Ping, Lu, Huchuan, Li, Zhenguo

Volltext bestellen

DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-Tuning von Xie, Enze, Yao, Lewei, Shi, Han, Liu, Zhili, Zhou, Daquan, Liu, Zhaoqiang, Li, Jiawei, Li, Zhenguo

Volltext bestellen

DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment von Yao, Lewei, Han, Jianhua, Liang, Xiaodan, Xu, Dan, Zhang, Wei, Li, Zhenguo, Xu, Hang

Volltext bestellen

PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis von Chen, Junsong, Yu, Jincheng, Ge, Chongjian, Yao, Lewei, Xie, Enze, Wu, Yue, Wang, Zhongdao, Kwok, James, Luo, Ping, Lu, Huchuan, Li, Zhenguo

Volltext bestellen

DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection von Yao, Lewei, Han, Jianhua, Wen, Youpeng, Liang, Xiaodan, Xu, Dan, Zhang, Wei, Li, Zhenguo, Xu, Chunjing, Xu, Hang

Volltext bestellen

G-DetKD: Towards General Distillation Framework for Object Detectors via Contrastive and Semantic-guided Feature Imitation von Yao, Lewei, Pi, Renjie, Xu, Hang, Zhang, Wei, Li, Zhenguo, Zhang, Tong

Volltext bestellen

DetGPT: Detect What You Need via Reasoning von Pi, Renjie, Gao, Jiahui, Diao, Shizhe, Pan, Rui, Dong, Hanze, Zhang, Jipeng, Yao, Lewei, Han, Jianhua, Xu, Hang, Kong, Lingpeng, Zhang, Tong

Volltext bestellen

SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection von Yao, Lewei, Xu, Hang, Zhang, Wei, Liang, Xiaodan, Li, Zhenguo

Volltext bestellen

PerceptionGPT: Effectively Fusing Visual Perception into LLM von Pi, Renjie, Yao, Lewei, Gao, Jiahui, Zhang, Jipeng, Zhang, Tong

Volltext

Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation von Yao, Lewei, Pi, Renjie, Xu, Hang, Zhang, Wei, Li, Zhenguo, Zhang, Tong

Volltext bestellen

FILIP: Fine-grained Interactive Language-Image Pre-Training von Yao, Lewei, Huang, Runhui, Hou, Lu, Lu, Guansong, Niu, Minzhe, Xu, Hang, Liang, Xiaodan, Li, Zhenguo, Jiang, Xin, Xu, Chunjing

Volltext bestellen

Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark von Gu, Jiaxi, Meng, Xiaojun, Lu, Guansong, Hou, Lu, Niu, Minzhe, Liang, Xiaodan, Yao, Lewei, Huang, Runhui, Zhang, Wei, Jiang, Xin, Xu, Chunjing, Xu, Hang

Volltext bestellen

DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detection von Yao, Lewei, Pi, Renjie, Han, Jianhua, Liang, Xiaodan, Xu, Hang, Zhang, Wei, Li, Zhenguo, Xu, Dan

Volltext

DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-Tuning von Xie, Enze, Yao, Lewei, Shi, Han, Liu, Zhili, Zhou, Daquan, Liu, Zhaoqiang, Li, Jiawei, Li, Zhenguo

Volltext

DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation von Mo, Shentong, Xie, Enze, Chu, Ruihang, Yao, Lewei, Hong, Lanqing, Nießner, Matthias, Li, Zhenguo

Volltext

PixArt-\Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation von Chen, Junsong, Ge, Chongjian, Xie, Enze, Wu, Yue, Yao, Lewei, Ren, Xiaozhe, Wang, Zhongdao, Luo, Ping, Lu, Huchuan, Li, Zhenguo

Volltext

DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment von Yao, Lewei, Han, Jianhua, Liang, Xiaodan, Xu, Dan, Zhang, Wei, Li, Zhenguo, Xu, Hang

Volltext